AlphaZero beats AlphaGo Zero, Stockfish, and Elmo

[Leo]

Not 10-0.

Result: +28 =72 -0

Was it to inconvenient to download the latest SF? You could also beef SF up with the cerebellum book. I don't trust these Google people at all. They spend way to much time saying what great things they are doing for humanity. Pride comes before the fall.

[jhellis3]

Lol, it wouldn't have mattered at all.

Though perhaps a better example would have been to train it for crazyhouse. SF is nearing 4000 "Elo" there, and the games are almost all decisive, so it would have been able to demonstrate its superiority much more clearly.

[Ras]

Was it to inconvenient to download the latest SF?

Because it isn't an official release and has not been tested as exhaustively. That's the point of releases. Just take a look at the TCEC what happened to Komodo when going with a dev version.

Besides, the release has been rated in many games while the "dev version of today" has not.

[pilgrimdan]

I agree with you.
Also what people who claim the HW was much faster..... what they don’t understand is that the thing learned from itself in a very short time!

What if we now give it 1 Year to further learn?


Side note, I looked at the games and they are really impressive!

I would not be surprised, if in a year's time it also starts speaking and thinking of itself.
I, Robot.

there may be a fine line
between self-learning
and self-consciousness ...

[Milos]

Was it to inconvenient to download the latest SF?

Because it isn't an official release and has not been tested as exhaustively. That's the point of releases. Just take a look at the TCEC what happened to Komodo when going with a dev version.

Besides, the release has been rated in many games while the "dev version of today" has not.

Oh so Google ppl actually cared that SF dev doesn't show some weakness due to it no being tested so they've chosen well tested version???
I guess that has something to do with Saint Nicholas Day today, I mean believing in Santa, etc.

[jhellis3]

So $100 US ok?

[IanO]

Speaking of which, I saw no mention of endgame tablebases used for either opponent. Anyone know if Stockfish had those available?

It would be interesting to see how well AlphaZero's endgame knowledge matches that of the endgame tablebases. If it performs well, it might actually be a smaller and more robust implementation of the same knowledge.

[Leo]

Lol, it wouldn't have mattered at all.

Though perhaps a better example would have been to train it for crazyhouse. SF is nearing 4000 "Elo" there, and the games are almost all decisive, so it would have been able to demonstrate its superiority much more clearly.

It would have mattered. It could have drawn more games. The score would have been different.

[Leo]

Was it to inconvenient to download the latest SF?

Because it isn't an official release and has not been tested as exhaustively. That's the point of releases. Just take a look at the TCEC what happened to Komodo when going with a dev version.

Besides, the release has been rated in many games while the "dev version of today" has not.

It is still unsatisfying to use that old of a SF.

[Leto]

Was it to inconvenient to download the latest SF?

Because it isn't an official release and has not been tested as exhaustively. That's the point of releases. Just take a look at the TCEC what happened to Komodo when going with a dev version.

Besides, the release has been rated in many games while the "dev version of today" has not.

It is still unsatisfying to use that old of a SF.

Judging from the score of the match it wouldn't matter if the latest SF dev were used, AlphaZero should dominate it easily. And that was with just 4 hours of training. Imagine how much stronger AlphaZero is now.